Paper Information Journal: MODARES JOURNAL OF ELECTRICAL ENGINEERING FALL 2010 , Volume 10 , Number 3; Page(s) 55 To 70. Paper: NONLINEAR MODELING OF SPEECH POINCARE SECTIONS IN COMBINATION WITH FREQUENCY ANALYSIS TO IMPROVE SPEECH RECOGNITION PERFORMANCE Author(s): JAFARI AYOUB*, ALMASGANJ F., NABI BIDHENDI M. * BIOMEDICAL ENGINEERING DEPARTMENT, ISLAMIC AZAD UNIVERSITY, QAZVIN BRANCH Abstract: This paper introduces a novel approach to improve performance of speech recognition systems using a combination of features obtained from speech reconstructed phase space (RPS) and frequency domain analysis. By choosing an appropriate value for the dimension, reconstructed phase space is assured to be topologically equivalent to the dynamics of the speech production system, and could therefore include information that may be absent in analysis approaches based on linear methods. Also, complicated systems such as speech production system can present cyclic and oscillatory patterns and Poincare sections could be used as an effective tool in analysis of such trajectories. In this research, a statistical modeling approach based on Gaussian Mixture models (GMM) was applied to the Poincare sections of speech RPS. The final feature set is obtained from a feature selection stage among parameters of GMM model and the usual Mel Frequency Cepstral coefficients (MFCC). An HMM-based speech recognition system and the TIMIT speech database are used to evaluate performance of the proposed feature extraction system for isolated and continuous speech recognition. Experiments represent about 5.7% absolute isolated phoneme recognition accuracy improvements in isolated phoneme recognition performance. The new approach is shown to be a viable and effective alternative to traditional feature extraction methods, particularly for signals such as speech with strong nonlinear characteristics. Keyword(s): RECONSTRUCTED PHASE SPACE (RPS), POINCARE SECTIONS, SPEECH RECOGNITION, FEATURE EXTRACTION, NON-LINEAR MODELING References: ندارد Persian Abstract Yearly Visit 68 See more details Twitter (1) Mendeley (14) Latest on Blog بررسی مدارک علمی مرتبط با آفلاتوکسینمقالات محققان ایرانی در 100 مقاله برتر بر اساس آلتمتریکسمندلی: شبکه اجتماعی رایگان برای رصد مدارک علمی از اسکوپوسبیشترین کلمات جستجو شده کاربران گوگل در سال 2019موضوعات جدید علمی را استخراج کنیدپابلونز : ابزاری رایگان برای رصد مقالات علمی از وب آو ساینس Enter SID Blog